The Impact of a Comprehensive Risk Prediction Model for Colorectal Cancer on a Population Screening Program

Abstract

Background: In many countries, population colorectal cancer (CRC) screening is based on age and family history, though more precise risk prediction could better target screening. We examined the impact of a CRC risk prediction model (incorporating age, sex, lifestyle, genomic, and family history factors) to target screening under several feasible screening scenarios.

Methods: We estimated the model's predicted CRC risk distribution in the Australian population. Predicted CRC risks were categorized into screening recommendations under 3 proposed scenarios to compare with current recommendations: 1) highly tailored, 2) 3 risk categories, and 3) 4 sex-specific risk categories. Under each scenario, for 35- to 74-year-olds, we calculated the number of CRC screens by immunochemical fecal occult blood testing (iFOBT) and colonoscopy and the proportion of predicted CRCs over 10 years in each screening group.

Results: Currently, 1.1% of 35- to 74-year-olds are recommended screening colonoscopy and 56.2% iFOBT, and 5.7% and 83.2% of CRCs over 10 years were predicted to occur in these groups, respectively. For the scenarios, 1) colonoscopy was recommended to 8.1% and iFOBT to 37.5%, with 36.1% and 50.1% of CRCs in each group; 2) colonoscopy was recommended to 2.4% and iFOBT to 56.0%, with 13.2% and 76.9% of cancers in each group; and 3) colonoscopy was recommended to 5.0% and iFOBT to 54.2%, with 24.5% and 66.5% of cancers in each group.

Conclusions: A highly tailored CRC screening scenario results in many fewer screens but more cancers in those unscreened. Category-based scenarios may provide a good balance between number of screens and cancers detected and are simpler to implement.

Figure 1.

Colorectal cancer (CRC) screening algorithm for current Australian guidelines and 2 proposed scenarios: CRC screening algorithm for scenarios 1 (current Australian guidelines), scenario 3 (using relative risks determined by risk prediction models), and scenario 4 (using sex-specific relative risks determined by risk prediction models, with an additional screening category for those slightly above “average” risk). FDR = first-degree relative; SDR = second-degree relative.

Figure 2.

Proportions and number of colorectal cancer (CRC) screens and predicted CRC in each screening group in 35- to 74-year-old Australians. The first column (bar chart) in each panel represents the proportion (95% confidence intervals of proportions, absolute number) of 35- to 74-year-old Australians who would not be screened for CRC, be screened with immunochemical fecal occult blood testing (iFOBT), and be screened with colonoscopy under each scenario. The second column (person icons) represents the proportion (95% confidence intervals of proportions, absolute number) of predicted CRC in the next 10 years that would occur in each of the screened groups. All scenarios (except scenario 1) use a combined lifestyle and genomic risk prediction model to place individuals in each screening group. A) Scenario 1, the current Australian guidelines. B) Scenario 2, a program based on absolute risk thresholds for screening using the risk prediction model. C) Scenario 3, a category-based program (3 categories not accounting for sex) using the risk prediction model. D) Scenario 4, a category-based program (4 categories accounting for sex) using the risk prediction model program. Some percentages do not sum to 100% due to rounding. The 95% confidence intervals for absolute numbers can be found in Supplementary Table 4 (available online).